{"id":"https://openalex.org/W3161135883","doi":"https://doi.org/10.32473/flairs.v34i1.128380","title":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model","display_name":"3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model","publication_year":2021,"publication_date":"2021-04-18","ids":{"openalex":"https://openalex.org/W3161135883","doi":"https://doi.org/10.32473/flairs.v34i1.128380","mag":"3161135883"},"language":"en","primary_location":{"id":"doi:10.32473/flairs.v34i1.128380","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.v34i1.128380","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/128380/130113","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journals.flvc.org/FLAIRS/article/download/128380/130113","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101908873","display_name":"Chengxi Li","orcid":"https://orcid.org/0000-0001-6086-1441"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chengxi Li","raw_affiliation_strings":["University of Kentucky"],"affiliations":[{"raw_affiliation_string":"University of Kentucky","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047163199","display_name":"Brent Harrison","orcid":"https://orcid.org/0000-0002-1301-5928"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Harrison","raw_affiliation_strings":["University of Kentucky Lexington, KY 40506"],"affiliations":[{"raw_affiliation_string":"University of Kentucky Lexington, KY 40506","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101908873"],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":0.2614,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"34","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8898271918296814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120166063308716},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6476141214370728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6071935892105103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5128898620605469},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5086775422096252},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.4807983934879303},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.475490927696228},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43292713165283203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3676409125328064},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36273813247680664},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3347536027431488}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8898271918296814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120166063308716},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6476141214370728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071935892105103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5128898620605469},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5086775422096252},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.4807983934879303},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.475490927696228},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43292713165283203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3676409125328064},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36273813247680664},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3347536027431488},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.32473/flairs.v34i1.128380","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.v34i1.128380","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/128380/130113","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:14a6b33b540d4c009a0b2fd72de4d582","is_oa":true,"landing_page_url":"https://doaj.org/article/14a6b33b540d4c009a0b2fd72de4d582","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the International Florida Artificial Intelligence Research Society Conference, Vol 34 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.32473/flairs.v34i1.128380","is_oa":true,"landing_page_url":"https://doi.org/10.32473/flairs.v34i1.128380","pdf_url":"https://journals.flvc.org/FLAIRS/article/download/128380/130113","source":{"id":"https://openalex.org/S4210205383","display_name":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","issn_l":"2334-0754","issn":["2334-0754","2334-0762"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310320363","host_organization_name":"George A. Smathers Libraries","host_organization_lineage":["https://openalex.org/P4310320363"],"host_organization_lineage_names":["George A. Smathers Libraries"],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International FLAIRS Conference Proceedings","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161135883.pdf","grobid_xml":"https://content.openalex.org/works/W3161135883.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1631260214","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2250384498","https://openalex.org/W2254252455","https://openalex.org/W2506483933","https://openalex.org/W2549139847","https://openalex.org/W2625940279","https://openalex.org/W2745461083","https://openalex.org/W2822349497","https://openalex.org/W2950178297","https://openalex.org/W2952640344","https://openalex.org/W2955956881","https://openalex.org/W2963758027","https://openalex.org/W2982260276","https://openalex.org/W2997248215","https://openalex.org/W6636811518","https://openalex.org/W6666761814","https://openalex.org/W6682631176","https://openalex.org/W6755592957","https://openalex.org/W6898505805","https://openalex.org/W6928992657"],"related_works":["https://openalex.org/W2952640344","https://openalex.org/W3139046135","https://openalex.org/W4229460020","https://openalex.org/W4312206189","https://openalex.org/W4375870165","https://openalex.org/W2884815824","https://openalex.org/W3009445007","https://openalex.org/W2781244421","https://openalex.org/W2808747415","https://openalex.org/W3161135883"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"build":[4],"a":[5,31,72],"multi-style":[6],"generative":[7],"model":[8,34,50,106],"for":[9,110],"stylish":[10],"image":[11,16],"captioning":[12],"which":[13],"uses":[14],"multi-modality":[15,37],"features,":[17,19],"ResNeXt":[18],"and":[20,39,65],"text":[21],"features":[22,38],"generated":[23],"by":[24,55],"DenseCap.":[25],"We":[26,44,69],"propose":[27],"the":[28,46,62,66],"3M":[29,105],"model,":[30],"Multi-UPDOWN":[32],"caption":[33],"that":[35],"encodes":[36],"decodes":[40],"them":[41],"into":[42],"captions.":[43,114],"demonstrate":[45],"effectiveness":[47],"of":[48,74],"our":[49,104],"on":[51,59,77],"generating":[52,111],"human-like":[53],"captions":[54],"examining":[56],"its":[57],"performance":[58],"two":[60],"datasets,":[61],"PERSONALITY-CAPTIONS":[63],"dataset,":[64],"FlickrStyle10K":[67],"dataset.":[68],"compare":[70],"against":[71],"variety":[73],"state-of-the-art":[75],"baselines":[76],"various":[78],"automatic":[79],"NLP":[80],"metrics":[81],"such":[82],"as":[83],"BLEU,":[84],"ROUGE-L,":[85],"CIDEr,":[86],"SPICE,":[87],"etc":[88],"\\footnote{code":[89],"will":[90],"be":[91,108],"available":[92],"at":[93],"https://github.com/cici-ai-club/3M}.":[94],"A":[95],"qualitative":[96],"study":[97],"has":[98],"also":[99],"been":[100],"done":[101],"to":[102],"verify":[103],"can":[107],"used":[109],"different":[112],"stylized":[113]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}